Earticle

초록

영어

The population based approach of GA allows large jumps in the search space. However
GAs has not proved successful for graph coloring because of the large degree of symmetry of the solution space. In fact, because of this symmetry mismatch it is very unlikely to produce a fit offspring when combining two good solutions. Thus GAs are often considered on inappropriate approach for problems such as graph coloring with a highly degenerate objective function. In order to compensate for this degeneracy we have applied Bitstream neuron (Boltzmann Machine) to the solution obtained from GA. Unlike traditional approaches of GA and ANN the proposed hybrid algorithm is guaranteed to have 100% convergence rate to valid solution with no parameter tuning. Experiments of such a hybrid algorithm are carried out on large DIMACS Challenge benchmark graphs. Results prove very competitive. Analysis of the behavior of the algorithm sheds light on ways to further improvement.

목차

Abstract
 1. Introduction
 2. Previous work
 3. Our work
 4. Experimental Result
 5. Conclusion
 References

저자

• Timir Maitra [ Heritage Institute of Technology ]
• Anindya J. Pal [ Heritage Institute of Technology ]
• Tai-hoon Kim [ Department of Multimedia, Hannam University, Daejeon, Korea ]
• Debnath Bhattacharyya [ Department of Multimedia, Hannam University, Daejeon, Korea ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of u- and e- Service, Science and Technology

• 간기

  격월간

• pISSN

  2005-4246

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605